cs.CVMar 29, 2026

LiDAR for Crowd Management: Applications, Benefits, and Future Directions

Authors: Abdullah Khanfor, Chaima Zaghouani, Hakim Ghazzai, Ahmad Alsharoa, Gianluca Setti

Organizations: the College of Computer Science and Information Systems, Najran University · College of Computer Science and Information Systems, Najran University, Najran, Saudi Arabia. · the College of Innovation & Technology, University of Michigan-Flint · College of Innovation & Technology, University of Michigan-Flint, MI, USA. · 

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Light Detection and Ranging (LiDAR) technology offers significant advantages for effective crowd management. This article presents LiDAR technology and highlights its primary advantages over other monitoring technologies, including enhanced privacy, performance in various weather conditions, and precise 3D mapping. We present a general taxonomy of four key tasks in crowd management: crowd detection, counting, tracking, and behavior classification, with illustrative examples of LiDAR applications for each task. We identify challenges and open research directions, including the scarcity of dedicated datasets, sensor fusion requirements, artificial intelligence integration, and processing needs for LiDAR point clouds. This article offers actionable insights for developing crowd management solutions tailored to public safety applications.

Figures & tables

Fig. 1 : Illustration of LiDAR scanning the crowd in public space.
Fig. 2 : Comparison of an RGB camera image versus a LiDAR point cloud for the same crowded scene generated using a simulator. LiDAR eliminates people’s faces and identifying features from collected data, preserving individual privacy in monitored areas.
FeatureLiDARRGB CameraThermal Camera
3D capabilityNative 3D point cloud2D images; depth via stereo or learning-based methods2D thermal map; limited depth perception
Field of viewWide (up to 360 ∘ depending on sensor model)Wide coverage achievable using fisheye lenses or multi-camera setupsLimited by lens (typically 40–90 ∘ )
Detection rangeUp to 200–300 m (high-resolution LiDAR)50–150 m (lens, resolution, and lighting dependent)10–50 m (sensor dependent)
Distance accuracyHigh – direct range measurement (cm-level)Moderate – depth inferred indirectlyLow to moderate – coarse distance estimation
Illumination requirementNone – active sensing, operates in darknessRequires sufficient lighting or IR assistanceNone – operates in darkness
PrivacyHigh – inherent privacy at sensing levelPrivacy achievable via system-level techniques (e.g., blurring, on-device analytics)Medium – body silhouettes without facial detail
TABLE I : Technical and Operational Comparison of Crowd Management Sensors
Fig. 3 : Representation of crowd management tasks and the analytical tools necessary for implementing effective crowd control strategies.
Fig. 4 : End-to-end AI-enabled LiDAR crowd management framework illustrating the main processing stages from data acquisition to crowd analysis tasks and decision support.
Fig. 5 : High-level, integrated taxonomy of LiDAR-based crowd management systems illustrating the relationships between point cloud types, crowd descriptors, analytical methods, core tasks, decision-making components, and application domains.
More in this topic

Crowd Counting

Crowd counting estimates how many people appear in images or video, supporting occupancy monitoring, safety planning, and crowd management.

See all 23 papers

Explore similar work

CardsList

  1. LiDAR for Rehabilitation: A Comprehensive Survey of Applications, AI Techniques, and Future Directions

    Apr 26, 2026Soumia Siyoucef, Najmeddine Dhieb, Hakim Ghazzai +3Gait Analysis

    Computer, Electrical and Mathematical Sciences & Engineering (CEMSE) Division at King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia · Valduce Hospital, Villa Beretta Rehabilitation Center, Costa Masnaga, Italy

  2. C-ARC: Continuous-Adaptive Range Clustering for Non-Repetitive LiDAR Sensors

    Jun 17, 2026Nick B. Schroeder, Jonathan Lichtenfeld, Oskar von StrykClusteringPoint Cloud Understanding

    Technical University of Darmstadt, Darmstadt, Germany · Technical University of Darmstadt, Hochschulstr. 10, 64289 Darmstadt, Germany. · Simulation, Systems Optimization and Robotics Group, Technical University of Darmstadt, Darmstadt, Germany +1

  3. LiDAR-based Crowd Navigation with Visible Edge Group Representation

    Apr 17, 2026Allan Wang, Aaron SteinfeldRobot NavigationSafe Robot Navigation

    1Miraikan, the National Museum of Emerging Science and Innovation, Tokyo, Japan. · 2the Robotics Institute, Carnegie Mellon University, Pittsburgh, USA.